Moving Object Detection Using Tensor-Based Low-Rank and Saliently Fused-Sparse Decomposition

doi:10.1109/TIP.2016.2627803

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 人工智能与机器学习（杨雪冰）-技术团队

	Moving Object Detection Using Tensor-Based Low-Rank and Saliently Fused-Sparse Decomposition
	Hu, Wenrui; Yang, Yehui; Zhang, Wensheng; Xie, Yuan
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2017-02-01
卷号	26 期号:2 页码:724-737
文章类型	Article
摘要	In this paper, we propose a new low-rank and sparse representation model for moving object detection. The model preserves the natural space-time structure of video sequences by representing them as three-way tensors. Then, it operates the low-rank background and sparse foreground decomposition in the tensor framework. On the one hand, we use the tensor nuclear norm to exploit the spatio-temporal redundancy of background based on the circulant algebra. On the other, we use the new designed saliently fused-sparse regularizer (SFS) to adaptively constrain the foreground with spatio-temporal smoothness. To refine the existing foreground smooth regularizers, the SFS incorporates the local spatio-temporal geometric structure information into the tensor total variation by using the 3D locally adaptive regression kernel (3D-LARK). What is more, the SFS further uses the 3D-LARK to compute the space-time motion saliency of foreground, which is combined with the l(1) norm and improves the robustness of foreground extraction. Finally, we solve the proposed model with globally optimal guarantee. Extensive experiments on challenging well-known data sets demonstrate that our method significantly outperforms the state-of-the-art approaches and works effectively on a wide range of complex scenarios.
关键词	Moving Object Detection Tensor Nuclear Norm Tensor Total Variation Space-time Visual Saliency
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TIP.2016.2627803
关键词[WOS]	BACKGROUND SUBTRACTION ; VISUAL SURVEILLANCE ; REGULARIZATION ; FRAMEWORK ; RECOVERY ; ROBUST ; IMAGE
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61402480 ; 61432008 ; 61472423 ; 61502495 ; 61532006)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000404773100010
引用统计	被引频次：51[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/15244
专题	多模态人工智能系统全国重点实验室_人工智能与机器学习（杨雪冰）-技术团队
作者单位	Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Hu, Wenrui,Yang, Yehui,Zhang, Wensheng,et al. Moving Object Detection Using Tensor-Based Low-Rank and Saliently Fused-Sparse Decomposition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2017,26(2):724-737.
APA	Hu, Wenrui,Yang, Yehui,Zhang, Wensheng,&Xie, Yuan.(2017).Moving Object Detection Using Tensor-Based Low-Rank and Saliently Fused-Sparse Decomposition.IEEE TRANSACTIONS ON IMAGE PROCESSING,26(2),724-737.
MLA	Hu, Wenrui,et al."Moving Object Detection Using Tensor-Based Low-Rank and Saliently Fused-Sparse Decomposition".IEEE TRANSACTIONS ON IMAGE PROCESSING 26.2(2017):724-737.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Final_Version.pdf（13016KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览